---
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: bert-mrpc-analysis
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# bert-mrpc-analysis

This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6197
- Accuracy: 0.8554
- F1: 0.8985

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     |
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
| 0.6445        | 0.2174 | 50   | 0.5860          | 0.7010   | 0.8201 |
| 0.5425        | 0.4348 | 100  | 0.5083          | 0.7647   | 0.8509 |
| 0.4903        | 0.6522 | 150  | 0.4756          | 0.7868   | 0.8621 |
| 0.459         | 0.8696 | 200  | 0.4043          | 0.8309   | 0.8832 |
| 0.3848        | 1.0870 | 250  | 0.3972          | 0.8505   | 0.8968 |
| 0.2851        | 1.3043 | 300  | 0.4763          | 0.8235   | 0.8808 |
| 0.2758        | 1.5217 | 350  | 0.3576          | 0.8701   | 0.9065 |
| 0.2241        | 1.7391 | 400  | 0.4367          | 0.8456   | 0.8919 |
| 0.2699        | 1.9565 | 450  | 0.3583          | 0.8554   | 0.8948 |
| 0.1345        | 2.1739 | 500  | 0.4947          | 0.8578   | 0.9    |
| 0.092         | 2.3913 | 550  | 0.5921          | 0.8505   | 0.8968 |
| 0.0825        | 2.6087 | 600  | 0.6000          | 0.8554   | 0.8985 |
| 0.1194        | 2.8261 | 650  | 0.6197          | 0.8554   | 0.8985 |


### Framework versions

- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1